Driving memory method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a driving memory method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a projection point corresponding to the current position of a vehicle in a memory driving map and first attribute information of a lane line around the projection point; and the vehicle is controlled according to the first attribute information of the lane lines and the second attribute information of the lane lines around the vehicle detected by the vehicle-mounted visual module, so that memory driving is realized, the purpose of memory driving without depending on a high-precision map is realized, vehicle-mounted hardware equipment does not need to be improved and upgraded, and the cost is reduced. And the implementation cost is low.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, and in particular to a memory driving method, device, electronic device and storage medium. Background Art

[0002] The vehicle's high-speed pilot assisted driving function means that after the vehicle enters a limited section of road, the vehicle can follow the navigation to autonomously select the correct route. In the middle of the way, it will also complete lane keeping, adaptive cruise control, avoidance, overtaking and lane changing according to factors such as road conditions and traffic environment.

[0003] At present, the high-speed pilot assisted driving function has a strong reliance on high-precision maps, and this function can only be enabled on certain roads in certain cities. At the same time, the initial investment of map manufacturers is large. The cost of a high-precision map collection vehicle is as high as several million. There are few people involved and the construction period is long. Therefore, only high-precision map information of some roads is collected at present. The coverage of cities and roads in high-precision maps is low. In some scenarios, regulations require that high-precision maps cannot be used. There is also the possibility that road maintenance personnel will modify the road section later. The cost of re-maintaining the road section is not less than the cost of initial mapping.

[0004] In view of this, this application is filed. Summary of the invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present disclosure provide a memory driving method, device, electronic device and storage medium, which do not require improvement or upgrade of the on-board hardware equipment and eliminate the dependence on high-precision maps.

[0006] In a first aspect, an embodiment of the present disclosure provides a memory driving method, the method comprising:

[0007] When the vehicle is in a memory driving state, obtaining a projection point corresponding to the current position of the vehicle and first attribute information of lane lines around the projection point in the memory driving map;

[0008] The vehicle is controlled according to the position information of the projection point, the first attribute information of the lane line, and the second attribute information of the lane line around the vehicle detected by the vehicle-mounted vision module to achieve memory driving.

[0009] In a second aspect, the embodiment of the present disclosure further provides a memory driving device, the device comprising:

[0010] An acquisition module, used for acquiring, when the vehicle is in a memory driving state, a projection point corresponding to the current position of the vehicle and first attribute information of lane lines around the projection point in the memory driving map;

[0011] A control module is used to control the vehicle according to the position information of the projection point, the first attribute information of the lane line, and the second attribute information of the lane line around the vehicle detected by the vehicle-mounted vision module, so as to realize memory driving.

[0012] In a third aspect, an embodiment of the present disclosure further provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the memory driving method as described above.

[0013] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the memory driving method as described above.

[0014] A memory driving method provided by an embodiment of the present disclosure obtains a projection point corresponding to the current position of the vehicle and first attribute information of lane lines around the projection point in a memory driving map when the vehicle is in a memory driving state, and controls the vehicle based on the position information of the projection point, the first attribute information of the lane lines, and second attribute information of the lane lines around the vehicle detected by an on-board vision module, so as to realize the technical means of memory driving, thereby achieving the purpose of memory driving without relying on high-precision maps, and without the need to improve or upgrade the on-board hardware equipment, with a low implementation cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0016] Figure 1 is a flow chart of a memory driving method in an embodiment of the present disclosure;

[0017] Figure 2 is a schematic diagram of marking lane lines in an embodiment of the present disclosure;

[0018] Figure 3 A schematic diagram of a construction process of a memory driving map in an embodiment of the present disclosure;

[0019] Figure 4 is a schematic diagram of a vehicle changing lanes in an embodiment of the present disclosure;

[0020] Figure 5 is a schematic diagram of a lane where a projection point is located in an embodiment of the present disclosure;

[0021] Figure 6 It is a schematic diagram of comparing visual information detected during memory driving with visual information in a memory map in an embodiment of the present disclosure;

[0022] Figure 7 A schematic diagram of updating lane lines in a memory driving map in an embodiment of the present disclosure;

[0023] Figure 8 A schematic diagram of another method of updating lane lines in a memory driving map in an embodiment of the present disclosure

[0024] Fig. 9 A schematic diagram of a process of updating a memory driving map in an embodiment of the present disclosure;

[0025] Fig.10 A schematic diagram of a working process of a memory driving system framework in an embodiment of the present disclosure;

[0026] Fig.11 A flowchart of a location information acquisition module S1 in an embodiment of the present disclosure

[0027] Fig.12 It is a structural schematic diagram of a memory driving device in an embodiment of the present disclosure;

[0028] Fig.13 It is a structural schematic diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0030] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0031] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0032] Figure 11 is a flow chart of a driving memory method in an embodiment of the present disclosure. The method can be executed by a driving memory device, which can be implemented in software and / or hardware, and can be configured in an electronic device. Figure 1 As shown, the method may specifically include the following steps:

[0033] S110. When the vehicle is in a memory driving state, obtain first attribute information of a projection point corresponding to the current position of the vehicle and lane lines around the projection point in the memory driving map.

[0034] Among them, the vehicle being in the memory driving state may mean that the vehicle's memory driving function is activated, or the vehicle enters the memory driving mode.

[0035] Specifically, in some embodiments, the vehicle may actively enter a memory driving state. For example, when the vehicle detects a memory driving route including the current location and the overlap between the route the vehicle has traveled and the memory driving route reaches a threshold, the vehicle actively enters the memory driving state.

[0036] Optionally, the vehicle can also passively enter the memory driving state, for example, when it detects that the user has triggered a certain operation, the vehicle enters the memory driving state. Exemplarily, when the vehicle is driving, it is determined whether there is a memory route; if there is a memory route, a prompt is issued whether to turn on the memory driving function; if an instruction to turn on the memory driving function is detected, the vehicle is controlled to enter the memory driving state. Furthermore, the user can trigger the instruction to turn on the memory driving function through the central control display in the cockpit. By issuing a prompt to the user whether to turn on the memory driving function when there is a memory route, the purpose of improving the user experience can be achieved; by controlling the vehicle to enter the memory driving state when an instruction to turn on the memory driving function is detected, the control accuracy can be improved, so that the control result is more in line with the user's intention, avoiding control results that the user does not expect, thereby improving the user experience.

[0037] Exemplarily, when the vehicle is traveling, determining whether there is a memory route includes:

[0038] Determine whether there is a memory route based on the real-time position of the vehicle. For example, if a memory route stored locally in the vehicle or in a cloud server corresponding to the vehicle includes the current real-time position of the vehicle, it can be determined that there is a memory route related to the current real-time position of the vehicle.

[0039] The memory driving map is a map that records a preset route and is a map of a smaller spatial range near the preset route. Therefore, the construction cost of the memory driving map is relatively low.

[0040] It can be understood that in order to ensure that the memory driving map is updated in time, when a new version of the memory driving map is generated, the new version of the memory driving map is used to replace the old version of the memory driving map. By ensuring the freshness of the memory driving map, the accuracy and driving efficiency of memory driving can be improved.

[0041] Optionally, the obtaining of the projection point corresponding to the current position of the vehicle in the memory driving map includes: determining the projection point corresponding to the current position of the vehicle in the memory driving map by a projection algorithm. For example, projection matching is performed by an ICP (Iterative Closest Point) algorithm to determine the projection point corresponding to the current position of the vehicle in the memory driving map.

[0042] S120, controlling the vehicle according to the position information of the projection point, the first attribute information of the lane line, and the second attribute information of the lane line around the vehicle detected by the on-board vision module to achieve memory driving.

[0043] The first lane attribute information is the map information generated when constructing the memory driving map, which belongs to the lane level information and is used for vehicle navigation and tracking. The vehicle memory driving function allows the vehicle to enter the memory driving section and complete lane keeping, adaptive cruise, avoidance, overtaking and lane changing according to factors such as navigation, road conditions and traffic environment.

[0044] Exemplarily, the first attribute information of the lane line includes one or more of the lane line, the identification of the corresponding lane line segment, the identification of the previous lane line segment connected to the corresponding lane line segment, the identification of the next lane line segment connected to the corresponding lane line segment, the width of the lane line in the corresponding lane line segment, the line type, the mapping status, the length, the sequence number, the road type, the distance between the vehicle driving trajectory point and the starting point of the corresponding lane line in the corresponding lane line segment, and the speed limit information of the lane.

[0045] The lane line mapping state includes a high-confidence state and a low-confidence state. Specifically, Figure 2As shown, when the vehicle 210 is traveling along a preset route (for the purpose of generating or updating a memory driving map), the mapping status of the lane line closest to the left side of the vehicle 210 (marking the lane line as the left lane line) and the lane line closest to the right side of the vehicle (marking the lane line as the right lane line) is a high-confidence state, and the mapping status of other lane lines (such as the left second lane line and the right second lane line) is a low-confidence state. It should be noted that if the lane line closest to the left side of the vehicle 210 is not detected by the on-board vision module when constructing the memory driving map, the left lane line does not exist in the constructed memory driving map. The road types include the type of entering the main road from the auxiliary road, and the type of entering the auxiliary road from the main road; specifically, the road type can be determined by the lane line width. When the width of the left lane line at the previous moment (for example, the 5th second) is greater than a certain value and is a dotted line, and the width of the right lane line at the current moment (for example, the 6th second) is also greater than the certain value and is a dotted line, then the road type is determined to be the type of entering the main road from the auxiliary road; if the width of the right lane line at the previous moment (for example, the 5th second) is greater than a certain value and is a dotted line, and the width of the left lane line at the current moment (for example, the 6th second) is also greater than the certain value and is a dotted line, then the road type is determined to be the type of entering the auxiliary road from the main road.

[0046] The speed limit information of the lane may be a speed limit value indicated by a speed limit sign, may be an average speed of the vehicle when traveling, or may be a larger one of the average speed of the vehicle when traveling and the speed limit value indicated by the speed limit sign.

[0047] Exemplarily, the controlling the vehicle according to the position information of the projection point, the first attribute information of the lane line, and the second attribute information of the lane line around the vehicle detected by the vehicle-mounted vision module to achieve memory driving includes:

[0048] The vehicle is laterally controlled according to the position information of the projection point and the second attribute information of the lane line, and the vehicle is longitudinally controlled according to the position information of the projection point and the first attribute information of the lane line. Specifically, when driving in the same lane, the vehicle is laterally controlled according to the lane line in the second attribute information of the lane line to prevent the vehicle from pressing the solid line, and the vehicle is longitudinally controlled according to the first attribute information of the lane line. For example, assuming that the vehicle is currently in the leftmost lane, and it is known through the memory of the driving map that the vehicle needs to complete the off-ramp process in the rightmost lane 1 km ahead, the vehicle can be controlled to change lanes to the right according to the lane line in the second attribute information of the lane line, and then based on the first attribute information of the lane line 1 km ahead (such as the lane position corresponding to the lane line segment and the connection relationship between adjacent segments, etc.), the vehicle will know when to get off the ramp and how to get off the ramp.

[0049] In an optional implementation, the vehicle can also be controlled to follow the vehicle's driving trajectory recorded in a memory driving map, and end-to-end driving on a preset route can also be achieved.

[0050] A memory driving method provided in an embodiment of the present application obtains a projection point corresponding to the current position of the vehicle and the first attribute information of the lane line around the projection point in a memory driving map when the vehicle is in a memory driving state, and controls the vehicle according to the position information of the projection point, the first attribute information of the lane line, and the second attribute information of the lane line around the vehicle detected by an on-board vision module, so as to realize the technical means of memory driving, thereby achieving the purpose of memory driving without relying on a high-precision map, and without the need to improve or upgrade the on-board hardware equipment, with a low implementation cost.

[0051] In particular, the memory driving method provided in the embodiment of the present application only needs to use the second attribute information of the lane line output by the intelligent front-view camera (i.e., the vehicle-mounted visual detection module) with the perception result, and currently, the intelligent front-view camera is basically installed on the passenger car, that is, the memory driving method provided in the embodiment of the present application only needs to be deployed on the vehicle and then matched with any product with a navigation function to complete the memory driving. Traditional mapping / online mapping requires the installation of a large number of cameras and laser radars, and the camera collects the complete original image. Generally speaking, due to the insufficient computing power of the on-board controller, offline mapping is performed, that is, the collected point cloud data + camera data + RTK (Real Time Kinematic, real-time dynamic measurement) data is taken, and offline synchronization, automatic mapping, manual correction and other operations can be completed. A controller with high computing power is also required, and most of the existing passenger car hardware computing power does not support this mode. It is necessary to install the missing hardware equipment (such as cameras, laser radars), and a high computing power chip is required, so the mapping cost is relatively high.

[0052] In addition, the memory driving method provided in the embodiment of the present application can ensure that the requirements of the navigation assistance function on perception and computing power are reduced without changing the back-end application layer (algorithm layer).

[0053] In general, the memory driving method provided in the embodiment of the present application can be applied to the highway navigation function system in the automatic driving system. There is no need for map manufacturers to spend high costs, high manpower and high energy in the early stage to create high-precision maps, and high costs for map maintenance in the later stage. It only requires manual driving in advance on frequently commuted highways, urban express roads or urban areas with clear lane lines to achieve a complete preset route. The memory driving function can be turned on the next time you drive, and the system will drive automatically to complete end-to-end automatic driving on the entire preset route.

[0054] On the basis of the above-mentioned embodiments, the construction scheme of the memory driving map is introduced below. The construction scheme provided by the embodiments of the present application can realize online mapping without the need for large computing power support and without the need to improve and upgrade the on-board hardware equipment. This can reduce the cost of mapping and provide a basis for eliminating the dependence of high-speed pilot assisted driving functions on high-precision maps.

[0055] Specifically, Figure 3 As shown, the construction scheme of the memory driving map includes the following steps:

[0056] S310. When the vehicle travels along a preset route, the positioning information of the vehicle and the third attribute information of the lane lines around the vehicle detected by the on-board vision module are obtained.

[0057] The preset route is usually a route that the user frequently travels, such as a commuting route from home to work or from work to home.

[0058] The positioning information of the vehicle may specifically include the longitude, latitude, altitude and heading angle of the vehicle. The specific method of obtaining the positioning information of the vehicle may be: preliminary positioning by using single-point or dual-point RTK. Specifically, after the RTK module is initialized and the positioning state meets the high-precision positioning requirements, an initial high-precision positioning information can be obtained. Then, the positioning information of the next moment is inferred based on the vehicle kinematic model by using IMU (Inertial Measurement Unit) to ensure that high-precision positioning information can still be obtained when the RTK module fails.

[0059] The vehicle-mounted vision module can use a currently mature functional product. The third attribute information of the lane line includes the line type, lane line width, lateral offset of each lane line from the vehicle in the vehicle coordinate system, speed limit information of traffic signs, and traffic light information. The definitions of the left second lane line, the left first lane line, the right first lane line, and the right second lane line can refer to the following: Figure 2 shown.

[0060] S320. Determine whether the lane line in the third attribute information of the lane line satisfies a segmentation condition based on a preset segmentation rule. If the segmentation condition is satisfied, segment the lane line to obtain a lane line segment.

[0061] Optionally, when the distance traveled by the vehicle along the preset route exceeds a certain threshold, step S320 may be executed again to avoid invalid segmentation, and the certain threshold may be 100 m.

[0062] Exemplarily, the determining whether the lane line in the third attribute information of the lane line satisfies the segmentation condition based on a preset segmentation rule includes:

[0063] For the current lane line in the third attribute information of the lane line, if the difference between the first lateral distance between the current lane line and the vehicle at the current moment and the second lateral distance between the current lane line and the vehicle at the previous moment is greater than the first threshold, it is determined that the segmentation condition is met; that is, when the vehicle changes lanes, it is determined that the segmentation condition is met and the lane line is segmented. Figure 4 As shown, assuming that the vehicle travels in the leftmost lane from the 1st second to the 30th second, and travels in the middle lane from the 30th second to the 50th second, the lane line is segmented at the 30th second, and the lane line is divided into two front and rear segments to obtain two lane line segments, each of which includes four lane lines that make up the lane. It can be understood that when determining whether a vehicle changes lanes, in addition to determining based on the lateral distance deviation between the vehicle and a lane line, it can also be determined based on the lateral distance deviation between multiple lane lines and the vehicle.

[0064] Alternatively, when the line type of the lane line changes, it is determined that the segmentation condition is met. Furthermore, in order to improve segmentation stability and reduce recognition errors, when the line type of the lane line changes and the continuous length of the lane line after the change reaches a threshold, it is determined that the segmentation condition is met. Alternatively, before determining whether the segmentation condition is met based on the line type of the lane line, the line type of the lane line is corrected, and the line type of the lane line with a shorter continuous length is corrected to the line type of its neighboring lane line. In this way, the lane lines with shorter lengths can be filtered out, and the purpose of improving segmentation stability and reducing recognition errors can also be achieved. For example, in some specific embodiments, before determining whether the lane line in the third attribute information of the lane line meets the segmentation condition based on the preset segmentation rule, the method also includes:

[0065] For each lane line in the third attribute information of the lane line, the continuous length of the lane lines with the same line type is counted; the status of the lane lines with a continuous length greater than the second threshold is marked as valid and reliable, and the status of the lane lines with a continuous length less than the second threshold and not the last lane line is marked as to be corrected (because the last lane line may be shorter due to the detection range of the visual detection module, so the last shorter lane line is not processed); for each lane line with the same line type, a reverse traversal is performed, and if the status of the current lane line is to be corrected, the line type of the current lane line is updated using the line types of other lane lines connected to the current lane line.

[0066] For example, in a specific implementation, if the status of the current lane line is to be corrected, it is determined whether the current lane line is the second-to-last lane line; if it is the second-to-last lane line and the status of the first-to-last lane line is valid and reliable, the line type of the first-to-last lane line is used to update the line type of the current lane line; if the current lane line is the second-to-last lane line and the status of the first-to-last lane line is to be corrected, the status of the current lane line is changed to valid and reliable, and all lane lines except the second-to-last lane line are updated using the line type of the previous lane line.

[0067] In another specific embodiment, the line type of the current lane line is updated by using the line type of the lane line that is connected to the current lane line in the last state as valid and reliable. If the forward order traversal is performed for each lane line of the same line type, the line type of the current lane line can be updated by using the line type of the lane line that is connected to the current lane line in the next state as valid and reliable.

[0068] By correcting the line type of a lane line with a shorter continuous length to the line type of its neighboring lane line, the lane line with a shorter length can be filtered out, thereby achieving the purpose of improving segmentation stability and reducing recognition errors.

[0069] S330, for each lane line segment, storing the first attribute information of the lane line in association with the positioning information to generate a memory driving map corresponding to the preset route.

[0070] Specifically, for example, for the current lane line segment, the track points of the vehicle traveling in the corresponding lane of the current lane line segment, the speed information at each track point, the speed limit information of the traffic sign, the line type, width, length, mapping status of the lane line, the corresponding road type, the lateral distance between each lane line point and the vehicle, the sequence number of each lane line in the current lane line segment (the sequence number is, for example, 0, 1, 2, 3... from left to right), the identifier of the current lane line segment (for example, the identifier of the first lane line segment can be recorded as 1, the identifier of the second lane line segment can be recorded as 2...), the identifier of the previous lane line segment connected to the current lane line segment, the identifier of the next lane line segment connected to the corresponding lane line segment, the distance between the vehicle's driving track point and the starting point of the corresponding lane line in the current lane line segment, and other lane line level information are stored for subsequent vehicle memory driving. In some embodiments, the existing memory driving map can also be updated using the second attribute information of the lane lines around the vehicle detected by the on-board visual module during each memory driving process of the vehicle to ensure the freshness of the memory driving map, thereby providing a basis for efficient and accurate memory driving.

[0071] Exemplarily, the memory driving method further includes:

[0072] The second lane line attribute information is compared with the first lane line attribute information to determine the target lane line information; wherein, compared with the lane line information in the memory driving map, the target lane line information may refer to newly added or modified lane line information.

[0073] Specifically, the first attribute information of the lane line also includes a first left lateral distance between the projection point and the nearest left lane line, and a first right lateral distance between the projection point and the nearest right lane line; the second attribute information of the lane line includes a second left lateral distance between the vehicle and the nearest left lane line, and a second right lateral distance between the vehicle and the nearest right lane line.

[0074] The comparing the second lane line attribute information with the first lane line attribute information to determine the target lane line information includes:

[0075] When the first left lateral distance and the second left lateral distance meet the matching condition (for example, when the absolute value of the difference between the first left lateral distance and the second left lateral distance is less than 1m, it is considered that the first left lateral distance and the second left lateral distance meet the matching condition), and the first right lateral distance and the second right lateral distance meet the matching condition (for example, when the absolute value of the difference between the first right lateral distance and the second right lateral distance is less than 1m, it is considered that the first right lateral distance and the second right lateral distance meet the matching condition), it indicates that the memory driving map is consistent with the physical space detected by the on-board vision module, the vehicle is indeed on the memory route, and there is indeed a matching memory driving map.

[0076] On the basis of satisfying the above matching conditions, if the mapping state of the nearest lane line on the left side of the projection point is low confidence (that is, when constructing the memory driving map, the nearest lane line on the left side of the projection point is not the left lane line, for example, Figure 5As shown, when the vehicle's projection point 510 is in memory driving, the nearest lane line on the left side is the lane line indicated by number 520; when constructing the memory driving map, the vehicle's projection point 530 is traveling in the right lane, so when constructing the memory driving map, the shooting of lane line 520 is not as clear as the shooting of lane lines 540 and 550, while lane line 520 can be clearly photographed during memory driving, so lane line 520 can be updated at this time), when the lane where the projection point is located is the leftmost lane, the information of the lane line on the left side of the vehicle in the second attribute information of the lane line (such as line width, line type, etc.) is determined as the target lane line information (when the lane where the projection point is located is the leftmost lane, the on-board vision module at this time may detect lane line information that was not detected during the last map construction, such as a newly added lane on the left side, so the information of the lane line on the left side of the vehicle in the second attribute information of the lane line is determined as the target lane line information, such as Figure 6 As shown, compared with constructing the memory driving map, a new lane is added to the road, so at this time, the information of the lane line on the left side of the vehicle in the second attribute information of the lane line is determined as the target lane line information); when the lane where the projection point is located is not the leftmost lane, the information of the lane line closest to the left side of the vehicle in the second attribute information of the lane line is determined as the target lane line information (that is, at this time, only the clearest lane line detected by the visual detection module is updated).

[0077] Similar to the above process, on the basis of satisfying the above matching conditions, if the mapping status of the nearest lane line on the right side of the projection point is low credibility, when the lane where the projection point is located is the rightmost lane, the information of the lane line on the right side of the vehicle in the second attribute information of the lane line is determined as the target lane line information; when the lane where the projection point is located is not the rightmost lane, the information of the lane line nearest to the right side of the vehicle in the second attribute information of the lane line is determined as the target lane line information.

[0078] And / or, comparing the second lane line attribute information with the first lane line attribute information to determine target lane line information, including:

[0079] When the mapping status of the nearest lane line on the left side of the projection point is high credibility (indicating that the nearest lane line on the left side of the projection point is the left lane line when constructing the memory driving map, and its credibility is relatively high), if the first left lateral distance and the second left lateral distance do not meet the matching condition (for example, when the original lane line is deleted due to road maintenance), when the serial number of the nearest lane line on the right side of the projection point is adjacent to the serial number of the nearest lane line on the left side of the projection point, the information of the nearest lane line on the left side of the vehicle in the second attribute information of the lane line is determined as the target lane line information (that is, the memory driving map is updated using the clearest lane line detected by the current on-board vision module), when the serial number of the nearest lane line on the right side of the projection point is not adjacent to the serial number of the nearest lane line on the left side of the projection point (indicating that when constructing the memory driving map, the on-board vision module may not detect more comprehensive lane line information due to occlusion or system detection and other problems), the information of the lane line on the left side of the vehicle in the second attribute information of the lane line is determined as the target lane line information.

[0080] If the first left lateral distance and the second left lateral distance meet the matching condition, when the lane where the projection point is located is the leftmost lane, the information of the left lane lines other than the nearest lane line on the left side of the vehicle in the second attribute information of the lane line is determined as the target lane line information; in essence, the nearest lane line on the left side of the current projection point is the first left lane line when constructing the memory driving map, and its credibility is relatively high, and the first left lateral distance and the second left lateral distance meet the matching condition, which further indicates that the memory driving map is accurate. At this time, it is only necessary to use the left second, left third and other lane line information detected by the on-board vision module to update the memory driving map.

[0081] Similar to the above process, when the mapping state of the nearest lane line on the right side of the projection point is high confidence, if the first right lateral distance and the second right lateral distance do not meet the matching condition, when the serial number of the nearest lane line on the right side of the projection point is adjacent to the serial number of the nearest lane line on the left side of the projection point, the information of the nearest lane line on the right side of the vehicle in the second attribute information of the lane line is determined as the target lane line information; when the serial number of the nearest lane line on the right side of the projection point is not adjacent to the serial number of the nearest lane line on the left side of the projection point, the information of the lane line on the right side of the vehicle in the second attribute information of the lane line is determined as the target lane line information; if the first right lateral distance and the second right lateral distance meet the matching condition, when the lane where the projection point is located is the rightmost lane, the information of the right lane lines other than the nearest lane line on the right side of the vehicle in the second attribute information of the lane line is determined as the target lane line information.

[0082] After determining the target lane line, the target lane line information is optimized to obtain processed target lane line information; the processed target lane line information is combined with the memory driving map to obtain an updated memory driving map.

[0083] Specifically, the optimizing the target lane line information to obtain the processed target lane line information includes:

[0084] The information of lane lines whose length is less than a third threshold value (e.g., 10 meters) and less than half of the length of the corresponding lane lines on the memory driving map in the target lane line information before processing is filtered out to obtain the filtered target lane line information; the purpose is to filter out shorter lane lines. If the lane lines are shorter, the probability of misidentification is higher, which can improve the overall map update accuracy. The line type of each lane line in the filtered target lane line information is corrected to obtain the processed target lane line information.

[0085] The step of correcting the line type of each lane line in the filtered target lane line information to obtain processed target lane line information includes:

[0086] Counting the number of lane lines whose length is greater than the third threshold in the filtered target lane line information, if the number is zero (indicating that the lane lines in the filtered target lane line information are all short, there may be problems, and the credibility is not high), correcting the line type of the lane line in the filtered target lane line information to the line type of the longest lane line in the filtered target lane line information;

[0087] If the number is not zero (indicating the existence of a longer credible lane line), then traverse the lane lines in the target lane line information whose length is less than the third threshold, and correct the line type of the first lane line whose length is less than the third threshold to the line type of the starting point of the corresponding lane line segment on the memory driving map; correct the line type of the last lane line whose length is less than the third threshold to the line type of the end point of the corresponding lane line segment on the memory driving map; correct the line type of other intermediate lane lines except the first and last lane lines of the lane line whose length is less than the third threshold to the line type of their respective neighbor lane lines.

[0088] The step of merging the processed target lane line information with the memory driving map to obtain an updated memory driving map includes:

[0089] For the original lane line not included in the processed target lane line information, retain the data corresponding to the original lane line in the memory driving map, and modify the identification of the corresponding lane line segment according to the relationship between the lane line in the processed target lane line information and the original lane line; Figure 7As shown, for example, updating the previous memory driving map (such as Figure 7 As shown on the left, the lane includes a 1000-meter-long lane, which consists of two lane lines. The lane is divided into two sections. 0-500 meters is the first section, and the corresponding lane line segment is marked as 1; 500-1000 meters is the second section, and the corresponding lane line segment is marked as 2. The updated memory driving map is as follows Figure 7 As shown on the right, this lane is lengthened by a section, and the identification of the corresponding lane line segment is adaptively modified according to the relationship between the lane line in the processed target lane line information and the original lane line. The original first segment becomes the second segment, and the identification is updated from 1 to 2. The original second segment becomes the third segment, and the identification is updated from 2 to 3.

[0090] For the lane line to be updated in the processed target lane line information, determine the original lane line segment corresponding to the lane line to be updated in the memory driving map, divide the original lane line segment according to the starting point and the end point of the lane line to be updated, obtain sub-segments of the original lane line segment, replace the corresponding sub-segment with the lane line to be updated, and synchronously store the information of the lane line to be updated, and modify the identifier of each sub-segment according to the identifier of the lane line segment before the divided original lane line segment; Figure 8 As shown, for example, updating the previous memory driving map (such as Figure 8 As shown on the left, a 1000-meter-long lane is composed of two lane lines. The lane is divided into two sections, 0-500 meters is the first section, and the corresponding lane line segment is marked as 1; 500-1000 meters is the second section, and the corresponding lane line segment is marked as 2; when updating the memory driving map, the first section is divided into two sections, 0-300 meters as one section and 300-500 meters as one section. Then, this 1000-meter-long lane is divided into 3 sections after updating, 0-300 meters as the first section, and the corresponding lane line segment is marked as 1; 300-500 meters as the second section, and the corresponding lane line segment is marked as 2; 500-1000 meters as the third section, and the corresponding lane line segment is marked as 3, as shown in FIG. Figure 8 Shown right.

[0091] The adjacent lane lines are aligned, and based on the alignment result, the adjacent lane lines with the same attributes are merged to obtain an updated memory driving map. The same attributes refer to the lane lines with the same line type and width.

[0092] The aligning of adjacent lane lines and merging of adjacent lane lines with the same attributes based on the alignment result include:

[0093] The distance between the end point of a lane line and the starting point of the next adjacent lane line is calculated. If the distance is less than a fourth threshold value (e.g., 80 cm), the end point of the lane line and the starting point of the next adjacent lane line are determined to be the same point, and the end point of the lane line is aligned with the starting point of the next adjacent lane line; if the end point of a lane line and the starting point of the next adjacent lane line are aligned, and the number of lanes corresponding to each is the same, and the lane line information of each adjacent lane line (e.g., lane line type, line width, mapping status, sequence number, etc.) is the same, then the lane line and the next adjacent lane line are merged into the same lane line.

[0094] In summary, in one embodiment, reference is made to Fig. 9 The process diagram of a memory driving map update shown in the figure specifically includes: when the map update function is turned on or the memory driving function is turned on, the projection point corresponding to the current position of the vehicle in the memory driving map and the first attribute information of the lane line around the projection point and the second attribute information of the lane line around the vehicle detected by the vehicle-mounted visual module are obtained, when the vehicle arrives near the destination or exceeds the preset geographical range, the second attribute information of the lane line is compared with the first attribute information of the lane line to determine the target lane line information, the target lane line information is optimized, and the processed target lane line information is obtained; the processed target lane line information is merged with the memory driving map to obtain the updated memory driving map, and the updated map is saved. In particular, when the data volume of the processed target lane line information is large, the data can be compressed in a certain way to improve the overall efficiency. Optionally, the processed target lane line information can be sampled to achieve the purpose of reducing the data volume.

[0095] For further reference, see Fig.10The workflow diagram of a memory driving system framework shown in the figure specifically includes: determining the location information of the vehicle through the location information acquisition module S1, determining the visual information around the vehicle through the visual information acquisition module S2, and when it is determined that it is the first time to build a map, the memory driving map building module S3 is used to build a map according to the information output by the location information acquisition module S1 and the visual information acquisition module S2 to obtain a memory driving map S5. When it is determined that it is not the first time to build a map, the memory driving map is updated by the memory driving update module S4. During the memory driving process (that is, when the navigation function is turned on), the vehicle's location information and the memory driving map are used as inputs to the high-precision map calculation module S5. The high-precision map calculation module S5 can output standard AdamisV2 / V3 data, which can be used by the navigation function systems provided by different manufacturers, that is, only the memory driving method provided in the embodiment of the present application needs to be deployed on the vehicle and then matched with any product with a navigation function to complete the memory driving. The information that can be output by the high-precision map calculation module S5 includes but is not limited to the following information: main vehicle position information (including offset from the planned starting point, current lane-level positioning information, distance to the destination, etc.); lane line segmentation information (number of segments, distance of segments from the planned starting point, road type of segments, speed limit information, number of segmented lanes information, segmented lane line type information, lane connection relationship, lane inheritance relationship, etc.); shape point information at a certain distance in front of the main vehicle (including center line shape point information, lane line shape point information, etc.).

[0096] The workflow diagram of the location information acquisition module S1 can be found in Fig.11 As shown, specifically: RTK initialization, determine whether it has entered a state where stable and reliable position information can be obtained. If so, predict the vehicle position information through the vehicle dynamics model and vehicle kinematics model, fuse the vehicle position information, and obtain the final vehicle position information.

[0097] Fig.12 FIG. 1 is a schematic diagram of the structure of a memory driving device in an embodiment of the present disclosure. Fig.12 As shown: the device includes: an acquisition module 1210 and a control module 1220.

[0098] Among them, the acquisition module 1210 is used to obtain the projection point corresponding to the current position of the vehicle and the first attribute information of the lane line around the projection point in the memory driving map when the vehicle is in the memory driving state; the control module 1220 is used to control the vehicle according to the position information of the projection point, the first attribute information of the lane line and the second attribute information of the lane line around the vehicle detected by the on-board vision module to realize memory driving.

[0099] The memory driving device provided in the embodiment of the present disclosure can execute the steps in the memory driving method provided in the method embodiment of the present disclosure, and can obtain the same beneficial effects, which will not be repeated here.

[0100] Fig.13 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Fig.13 , which shows a structural schematic diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure. Fig.13 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0101] like Fig.13 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes to implement the method of the embodiment described in the present disclosure according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage device 508 to the random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0102] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart, thereby realizing the memory driving method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0103] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0104] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the memory driving method:

[0105] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0106] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0107] Solution 1: A memory driving method, the method comprising:

[0108] When the vehicle is in a memory driving state, obtaining a projection point corresponding to the current position of the vehicle and first attribute information of lane lines around the projection point in the memory driving map;

[0109] The vehicle is controlled according to the position information of the projection point, the first attribute information of the lane line, and the second attribute information of the lane line around the vehicle detected by the vehicle-mounted vision module to achieve memory driving.

[0110] Solution 2: The method according to Solution 1 further includes:

[0111] While the vehicle is traveling, determining whether a memory route exists;

[0112] If there is a memory route, a prompt will be given whether to turn on the memory driving function;

[0113] If a command to start the memory driving function is detected, the vehicle is controlled to enter a memory driving state.

[0114] Solution 3: According to the method of Solution 2, when the vehicle is traveling, determining whether there is a memory route includes:

[0115] Whether a memory route exists is determined based on the real-time position of the vehicle.

[0116] Solution 4: According to the method of Solution 1, the vehicle is controlled according to the position information of the projection point, the first attribute information of the lane line, and the second attribute information of the lane line around the vehicle detected by the vehicle-mounted vision module to achieve memory driving, including:

[0117] The vehicle is laterally controlled according to the position information of the projection point and the second attribute information of the lane line, and the vehicle is longitudinally controlled according to the position information of the projection point and the first attribute information of the lane line.

[0118] Solution 5. According to the method described in Solution 1, the first attribute information of the lane line includes the lane line, the identification of the corresponding lane line segment, the identification of the previous lane line segment connected to the corresponding lane line segment, the identification of the next lane line segment connected to the corresponding lane line segment, the width of the lane line in the corresponding lane line segment, the line type, the mapping status, the length, the sequence number, the road type, the distance between the vehicle driving trajectory point and the starting point of the corresponding lane line in the corresponding lane line segment, and the speed limit information of the lane.

[0119] Solution 6. The method according to any one of solutions 1 to 5, further comprising:

[0120] When the vehicle travels along a preset route, obtaining positioning information of the vehicle and third attribute information of lane lines around the vehicle detected by an on-board vision module;

[0121] Based on a preset segmentation rule, determining whether the lane line in the third attribute information of the lane line meets a segmentation condition, and if the segmentation condition is met, segmenting the lane line to obtain a lane line segment;

[0122] For each lane line segment, the first attribute information of the lane line is associated and stored according to the positioning information to generate a memory driving map corresponding to the preset route.

[0123] Solution 7: According to the method of Solution 6, the step of determining whether the lane line in the third attribute information of the lane line satisfies the segmentation condition based on a preset segmentation rule includes:

[0124] For the current lane line in the third attribute information of the lane line, if the difference between a first lateral distance between the current lane line and the vehicle at a current moment and a second lateral distance between the current lane line and the vehicle at an adjacent previous moment is greater than a first threshold, it is determined that the segmentation condition is met;

[0125] Alternatively, when the line type of the lane line changes, it is determined that the segmentation condition is met.

[0126] Solution 8. According to the method of Solution 7, before determining whether the lane line in the third attribute information of the lane line meets the segmentation condition based on the preset segmentation rule, the method further includes:

[0127] For each lane line in the third attribute information of the lane line, counting the continuous length of lane lines of the same line type;

[0128] The state of the lane line whose continuous length is greater than the second threshold is marked as valid and reliable, and the state of the lane line whose continuous length is less than the second threshold and is not the last lane line is marked as to be corrected;

[0129] For each lane line of the same line type, perform a reverse traversal. If the status of the current lane line is to be corrected, the line type of the current lane line is updated using the line types of other lane lines connected to the current lane line.

[0130] Solution 9. The method according to Solution 6 further includes:

[0131] Comparing the second lane line attribute information with the first lane line attribute information to determine target lane line information;

[0132] Optimizing the target lane line information to obtain processed target lane line information;

[0133] The processed target lane line information is combined with the memory driving map to obtain an updated memory driving map.

[0134] Solution 10. According to the method described in Solution 9, the first attribute information of the lane line also includes a first left lateral distance between the projection point and the nearest left lane line, and a first right lateral distance between the projection point and the nearest right lane line; the second attribute information of the lane line includes a second left lateral distance between the vehicle and the nearest left lane line, and a second right lateral distance between the vehicle and the nearest right lane line;

[0135] The comparing the second lane line attribute information with the first lane line attribute information to determine the target lane line information includes one or more of the following:

[0136] When the first left lateral distance and the second left lateral distance meet a matching condition, and the first right lateral distance and the second right lateral distance meet a matching condition, if the mapping state of the nearest lane line on the left side of the projection point is low credibility, when the lane where the projection point is located is the leftmost lane, the information of the lane line on the left side of the vehicle in the second attribute information of the lane line is determined as the target lane line information, and when the lane where the projection point is located is not the leftmost lane, the information of the lane line on the left side of the vehicle in the second attribute information of the lane line is determined as the target lane line information; if the mapping state of the nearest lane line on the right side of the projection point is low credibility, when the lane where the projection point is located is the rightmost lane, the information of the lane line on the right side of the vehicle in the second attribute information of the lane line is determined as the target lane line information, and when the lane where the projection point is located is not the rightmost lane, the information of the lane line on the right side of the vehicle in the second attribute information of the lane line is determined as the target lane line information;

[0137] When the mapping state of the nearest lane line on the left side of the projection point is high confidence, if the first left lateral distance and the second left lateral distance do not meet the matching condition, when the sequence number of the nearest lane line on the right side of the projection point is adjacent to the sequence number of the nearest lane line on the left side of the projection point, the information of the nearest lane line on the left side of the vehicle in the second attribute information of the lane line is determined as the target lane line information; when the sequence number of the nearest lane line on the right side of the projection point is not adjacent to the sequence number of the nearest lane line on the left side of the projection point, the information of the lane line on the left side of the vehicle in the second attribute information of the lane line is determined as the target lane line information; if the first left lateral distance and the second left lateral distance meet the matching condition, when the lane where the projection point is located is the leftmost lane, the information of the left lane lines other than the nearest lane line on the left side of the vehicle in the second attribute information of the lane line is determined as the target lane line information;

[0138] When the mapping state of the nearest lane line on the right side of the projection point is high confidence, if the first right lateral distance and the second right lateral distance do not meet the matching condition, when the serial number of the nearest lane line on the right side of the projection point is adjacent to the serial number of the nearest lane line on the left side of the projection point, the information of the nearest lane line on the right side of the vehicle in the second attribute information of the lane line is determined as the target lane line information; when the serial number of the nearest lane line on the right side of the projection point is not adjacent to the serial number of the nearest lane line on the left side of the projection point, the information of the lane line on the right side of the vehicle in the second attribute information of the lane line is determined as the target lane line information; if the first right lateral distance and the second right lateral distance meet the matching condition, when the lane where the projection point is located is the rightmost lane, the information of the right lane lines other than the nearest lane line on the right side of the vehicle in the second attribute information of the lane line is determined as the target lane line information.

[0139] Solution 11: According to the method of Solution 9, the step of optimizing the target lane line information to obtain the processed target lane line information includes:

[0140] Filtering out lane line information whose length is less than a third threshold and less than half of the length of a corresponding lane line on the memory driving map from the target lane line information before processing, to obtain filtered target lane line information;

[0141] The line type of each lane line in the filtered target lane line information is corrected to obtain processed target lane line information.

[0142] Solution 12: According to the method of Solution 11, the line type of each lane line in the filtered target lane line information is corrected to obtain the processed target lane line information, including:

[0143] Counting the number of lane lines whose length is greater than the third threshold in the filtered target lane line information, and if the number is zero, correcting the line type of the lane line in the filtered target lane line information to the line type of the longest lane line in the filtered target lane line information;

[0144] If the number is not zero, traverse the lane lines in the target lane line information whose length is less than the third threshold, and correct the line type of the first lane line among the lane lines whose length is less than the third threshold to the line type of the corresponding lane line starting point on the memory driving map; correct the line type of the last lane line among the lane lines whose length is less than the third threshold to the line type of the corresponding lane line end point on the memory driving map; correct the line type of other middle lane lines except the first and last lane lines among the lane lines whose length is less than the third threshold to the line type of their respective neighbor lane lines.

[0145] Solution 13: According to the method of Solution 9, the step of merging the processed target lane line information with the memory driving map to obtain an updated memory driving map includes:

[0146] For the original lane line not included in the processed target lane line information, retain the data corresponding to the original lane line in the memory driving map, and modify the identification of the corresponding lane line segment according to the relationship between the lane line in the processed target lane line information and the original lane line;

[0147] For the lane line to be updated in the processed target lane line information, determine the original lane line segment corresponding to the lane line to be updated in the memory driving map, divide the original lane line segment according to the starting point and the end point of the lane line to be updated, obtain sub-segments of the original lane line segment, replace the corresponding sub-segment with the lane line to be updated, synchronously store the information of the lane line to be updated, and modify the identifier of each sub-segment according to the identifier of the lane line segment before the divided original lane line segment;

[0148] Adjacent lane lines are aligned, and adjacent lane lines with the same attributes are merged based on the alignment result to obtain an updated memory driving map.

[0149] Solution 14: According to the method of Solution 13, the adjacent lane lines are aligned, and the adjacent lane lines with the same attributes are merged based on the alignment result, including:

[0150] Calculating the distance between an end point of a lane line and a starting point of an adjacent next lane line, and if the distance is less than a fourth threshold, determining that the end point of the lane line and the starting point of the adjacent next lane line are the same point, and aligning the end point of the lane line with the starting point of the adjacent next lane line;

[0151] If the end point of a lane line is aligned with the starting point of the next adjacent lane line, and the corresponding number of lanes is the same, and the lane line information of the respective adjacent lane lines is the same, then the lane line and the next adjacent lane line are merged into the same lane line.

[0152] Solution 15. The method according to Solution 9 further includes:

[0153] The memory driving map before the update is replaced with the updated memory driving map.

[0154] Solution 16: A memory driving device, comprising:

[0155] An acquisition module, used for acquiring, when the vehicle is in a memory driving state, a projection point corresponding to the current position of the vehicle and first attribute information of lane lines around the projection point in the memory driving map;

[0156] A control module is used to control the vehicle according to the position information of the projection point, the first attribute information of the lane line, and the second attribute information of the lane line around the vehicle detected by the vehicle-mounted vision module, so as to realize memory driving.

[0157] Solution 17. An electronic device, comprising:

[0158] one or more processors;

[0159] A storage device for storing one or more programs;

[0160] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of schemes 1-15.

[0161] Solution 18. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of Solution 1 to Solution 15.

[0162] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

Claims

1. A memory driving method, characterized in that: The method comprises: When the vehicle is in a memory driving state, obtaining a projection point corresponding to the current position of the vehicle and first attribute information of lane lines around the projection point in the memory driving map; The vehicle is controlled according to the position information of the projection point, the first attribute information of the lane line, and the second attribute information of the lane line around the vehicle detected by the vehicle-mounted vision module to achieve memory driving.

2. The method according to claim 1, characterized in that Also includes: While the vehicle is traveling, determining whether a memory route exists; If there is a memory route, a prompt will be given whether to turn on the memory driving function; If a command to start the memory driving function is detected, the vehicle is controlled to enter a memory driving state.

3. The method according to claim 2, characterized in that The determining whether there is a memory route when the vehicle is traveling includes: Whether a memory route exists is determined based on the real-time position of the vehicle.

4. The method according to claim 1, characterized in that The controlling the vehicle according to the position information of the projection point, the first attribute information of the lane line, and the second attribute information of the lane line around the vehicle detected by the vehicle-mounted vision module to realize memory driving includes: The vehicle is laterally controlled according to the position information of the projection point and the second attribute information of the lane line, and the vehicle is longitudinally controlled according to the position information of the projection point and the first attribute information of the lane line.

5. The method according to claim 1, characterized in that The first attribute information of the lane line includes one or more of the lane line, the identifier of the corresponding lane line segment, the identifier of the previous lane line segment connected to the corresponding lane line segment, the identifier of the next lane line segment connected to the corresponding lane line segment, the width, line type, mapping status, length, sequence number, road type of the lane line in the corresponding lane line segment, the distance between the vehicle driving trajectory point and the starting point of the corresponding lane line in the corresponding lane line segment, and the speed limit information of the lane.

6. The method according to any one of claims 1 to 5, characterized in that: Also includes: When the vehicle travels along a preset route, obtaining positioning information of the vehicle and third attribute information of lane lines around the vehicle detected by an on-board vision module; Based on a preset segmentation rule, determining whether the lane line in the third attribute information of the lane line meets a segmentation condition, and if the segmentation condition is met, segmenting the lane line to obtain a lane line segment; For each lane line segment, the first attribute information of the lane line is associated and stored according to the positioning information to generate a memory driving map corresponding to the preset route.

7. The method according to claim 6, characterized in that The determining whether the lane line in the third attribute information of the lane line satisfies the segmentation condition based on the preset segmentation rule includes: For the current lane line in the third attribute information of the lane line, if the difference between a first lateral distance between the current lane line and the vehicle at a current moment and a second lateral distance between the current lane line and the vehicle at an adjacent previous moment is greater than a first threshold, it is determined that the segmentation condition is met; Alternatively, when the line type of the lane line changes, it is determined that the segmentation condition is met.

8. A memory driving device, characterized in that: include: An acquisition module, used for acquiring, when the vehicle is in a memory driving state, a projection point corresponding to the current position of the vehicle and first attribute information of lane lines around the projection point in the memory driving map; A control module is used to control the vehicle according to the position information of the projection point, the first attribute information of the lane line, and the second attribute information of the lane line around the vehicle detected by the vehicle-mounted vision module, so as to realize memory driving.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images